Title :
Analyzing state dynamics in a recurrent neural network
Author :
Spiegel, Rainer ; Suret, Mark ; Le Pelley, M.E. ; McLaren, I.P.L.
Author_Institution :
Dept. of Exp. Psychol., Cambridge Univ., UK
fDate :
6/24/1905 12:00:00 AM
Abstract :
An analysis of state in simple recurrent networks is presented when they are trained to predict the outputs in a finite state grammar, and when they are required to generalize to a similar grammar
Keywords :
grammars; learning (artificial intelligence); recurrent neural nets; finite state grammar; recurrent neural network; state dynamics; Application software; Computer science; Context modeling; Electrical engineering; Humans; Intelligent networks; Nonlinear systems; Psychology; Recurrent neural networks; Taxonomy;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005582
